ilastik
the interactive learning and segmentation toolkit
ilastik is a simple, user-friendly tool for interactive image classification, segmentation and analysis. It is built as a modular software framework, which currently has workflows for automated (supervised) pixel- and object-level classification, automated and semi-automated object tracking, semi-automated segmentation and object counting without detection. Most analysis operations are performed lazily, which enables targeted interactive processing of data subvolumes, followed by complete volume analysis in offline batch mode. Using it requires no experience in image processing.
Pixel Classification
Train using simple brush strokes
Pixel Classification
Semantic segmentation using predicted class probabilities
Object classification
Predict the semantic class of objects
Carving
Extract objects from a 3D volume semi-automatically
Pixel Features
Select from a simple set of predefined image features
Counting
Count densely packed cells
Tracking
utomatic and manual tracking of dividing cells (2D+3D)
Release 1.3.0 is out of beta!
We are happy to announce a new ilastik release, based on Python3 and Qt5! Detailed release notes can be found here, in short, it's much better, go ahead and try! The GUI is faster, the tracking does not need CPLEX, we have new export formats, and much more.
New video tutorial
We started doing video tutorials again: Pixel Classification. If you like it, get back to us and we'll do one on your favorite topic!
Get in touch
Discuss with other users at forum.image.sc or contact the friendly ilastik team directly.